An Explainable Bayesian TimesNet for Probabilistic Groundwater Level Prediction
Water Resources Research · 2025-06 · 61 (6)
DOI: 10.1029/2025wr040191 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water Resources Research, online erschienen am 02.06.2025. Verfasst von Zechen Peng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Reliable groundwater level (GWL) prediction is essential for sustainable water resources management. Despite recent advances in machine learning (ML) methods for GWL prediction, further improvements may be made in uncertainty quantification and model interpretability. This study proposes Bayesian TimesNet (BTimesNet), a novel deep learning model for probabilistic and explainable GWL prediction. BTimesNet transforms 1D time series data into 2D matrices based on periodicity, enhancing the capture of temporal patterns through convolutional filters. A Bayesian framework using Stein Variational Gradient Descent is implemented to quantify predictive uncertainties. For model interpretability, SHapely Additive exPlanations (SHAP) is utilized to quantify predictor contributions. The efficacy of BTimesNet for multi‐step‐ahead GWL prediction is evaluated using monthly data collected from 19 monitoring wells across three hydroclimatic regions in the U.S., and compared against the widely used long short‐term memory (LSTM) and Autoformer models. Results show that BTimesNet consistently outperforms LSTM and Autoformer, providing more accurate predictions up to 4 months ahead. SHAP analysis reveals that historical GWLs are the most informative features, with meteorological predictors making secondary contributions. BTimesNet's superior performance stems from its ability to extract both short‐ and long‐term temporal features. This approach represents a valuable advancement for accurate GWL prediction and risk‐informed decision‐making, providing critical lead time for proactive groundwater and ecosystem management and agricultural irrigation planning. Its data‐driven nature also facilitates broader applications across hydrological and environmental prediction domains.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Peng, Z., Mo, S., Sun, A. Y., Wu, J., Zeng, X., Lu, M., & Shi, X. (2025). An Explainable Bayesian TimesNet for Probabilistic Groundwater Level Prediction. Water Resources Research, 61(6). https://doi.org/10.1029/2025wr040191
Vancouver
Peng Z, Mo S, Sun AY, Wu J, Zeng X, Lu M, et al. An Explainable Bayesian TimesNet for Probabilistic Groundwater Level Prediction. Water Resources Research. 2025;61(6). doi:10.1029/2025wr040191
BibTeX
@article{Peng2025,
author = {Peng, Zechen and Mo, Shaoxing and Sun, Alexander Y. and Wu, Jichun and Zeng, Xiankui and Lu, Miao and Shi, Xiaoqing},
title = {An Explainable Bayesian TimesNet for Probabilistic Groundwater Level Prediction},
journal = {Water Resources Research},
year = {2025},
volume = {61},
number = {6},
doi = {10.1029/2025wr040191}
}
EUVIMED